Sign inSign up
Introduction to CNNs thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Introduction to CNNs

Published on Jul 27, 20176783 Views

Richard Zemel

DLSS & RLSS 2017 - Montreal

Related categories

Deep LearningReinforcement LearningUnsupervised Learning

Chapter list

Introduction to Convolutional Networks
 - 100:00
Introduction to Convolutional Networks
 - 200:13
Vector Institute Faculty01:52
We’re hiring!!02:22
Outline   03:16
Neural Networks  for  Object Recogniton - 103:58
Neural Networks for Object Recogniton - 204:34
Neural Networks for Object Recogniton - 305:03
Neural Networks for Object Recogniton - 405:34
The  invariance  problem05:57
Applying  neural  nets  to  images06:17
Local  Receptive  Fields07:35
Topographic  Maps08:33
Local  Receptive  Fields - 109:30
Local  Receptive  Fields - 209:57
Shared  Weights11:24
Examples  of  Feature  Detectors13:23
Local  RFs  14:27
Weight  sharing:  Parameter  saving15:13
Pooling17:32
Convolutional  Layer22:15
Finishing  it  off22:49
Le  Net  25:07
Outline   26:33
Modern  CNNs:  Alexnet  (2012)  26:37
VGG  (2014)  28:33
Residual  Networks  (2015)  28:56
Highway  Networks  (2015)30:43
How  Deep?    31:52
How  Deep?  Good?  32:20
How  Deep?  Good?  Slow?  34:06
How  Deep?  Good?  Slow?  Complex?  35:04
Recent Developments  in  CNNs36:19
Normalization  38:57
Divisive Normalizaton - 1   40:47
Divisive Normalizaton - 242:16
Network  Design:  Recep/ve  Fields43:16
Effec/ve  Recep/ve  Fields45:19
Enlarging Effective Recep/ve  Fields47:00
Outline48:51
Representations in CNNs 49:03
CNNs & Biology 49:22
Original CNN: Bio-inspired 50:42
CNNs & Biology 51:32
Visualizing the Representations - 155:29
Visualizing the Representations - 257:20
Visualizing the Representations - 359:04
Visualizing the Representations - 459:20
Analyzing the Representations 01:00:11
Parts-Based Representations 01:01:25
Analyzing the Representations 01:03:17
Theory of CNNs 01:04:58
Representations  in  very  deep  nets01:08:59
Outline01:12:21
Applications:  Semantic  Segmentation01:12:33
Up-­‐sampling  with  convolu/ons  01:14:15
De-convolution01:15:33
Applying  to  semantic  segmentation01:16:11
Outline   01:16:43
Cap+oning  via  Image/Text  Embedding01:17:30
Ranking  experiments:  Flickr8K  and   Flickr30K  01:20:08
Genera+ng  via  encoder-­‐decoder  model01:22:05
Encoder-­‐decoder  model01:22:43
How  to  generate  descrip+ons01:22:55
Some  good  results  -­‐  generation01:23:26
Some  failure  types01:23:38
Mad  Libs01:24:31
Generate  with  style - 101:24:32
Generate with style - 201:25:27
Generate with style - 301:25:48
Visual  Question-­‐Answering01:26:11
Outline   01:26:12
Modern  Deep  Learning:More  Data  →  Becer  Results01:26:22
Conclusion - 101:26:50
Conclusion - 201:27:36